Slope deformation prediction method of multi-core TCN network under feature screening

The embodiment of the invention provides a slope deformation prediction method of a multi-core TCN network under feature screening, and the method comprises the steps: determining a slope deformation quantity and a deformation impact factor corresponding to a target monitoring region of a to-be-moni...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: ZHANG JIAHAO, WAN JIASHAN, WANG WEIKE, ZHANG JIABIN, LYU HAIRUI, BAI YANG, WU ZHENHAO, XIA NA
Format: Patent
Sprache:chi ; eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The embodiment of the invention provides a slope deformation prediction method of a multi-core TCN network under feature screening, and the method comprises the steps: determining a slope deformation quantity and a deformation impact factor corresponding to a target monitoring region of a to-be-monitored slope, the slope deformation quantity is used for representing the deformation quantity of the target monitoring area occurring at the current moment compared with the previous moment, and the deformation influence factors are used for representing factors influencing slope deformation; on the basis of the slope deformation quantity and the mutual information value of the deformation influence factor, performing feature screening on the deformation influence factor to obtain a strong correlation factor; and constructing a corresponding time sequence feature based on the strong correlation factor, and determining a slope deformation quantity prediction result of the target monitoring area at the next moment ba